ICSA Colloquium Talk - 15/09/2022

Title:  "SoCodeCNN: Program Source Code for Visual CNN Classification Using Computer Vision Methodology"

Abstract:  Automated feature extraction from program source-code such that proper computing resources could be allocated to the program, which is very difficult given the current state of technology. Therefore, conventional methods call for skilled human intervention in order to achieve the task of feature extraction from programs. This talk introduces a research and methodology called SoCodeCNN, which is based on a human-inspired approach to automatically convert program source-codes to visual images. The images could be then utilized for automated classification by visual convolutional neural network (CNN) based algorithm. The proposed methodology could be utilized in plethora of application in understanding and extracting features from program source code.  

Bio:  Somdip Dey FRSA is a PhD graduand in the field of embedded machine learning at the University of Essex. He is widely credited as the co-developer of the nosh app - an embedded machine learning powered food management application that helps consumers to optimize food consumption and reduce food waste. He is the co-founder and CEO of Nosh Technologies, a leading deep tech company reducing food waste and hunger by leveraging technology. Dey is also a Lecturer of Computer Science at the University of Essex and a Professor of Practice at Woxsen University. He has been named a Life Fellow of the Royal Society of Arts, an MIT Innovator Under 35 and a World IP Review Leader for his contributions in developing embedded machine learning technologies to improve sustainability of the society.